Directorio de modelos de IA — Generación de vídeo, imagen y audio
Explora y prueba 125 modelos de 16 proveedores. Abre cualquier tarjeta para probar el modelo en el playground.
Los precios por variante de cada submodelo están en la página de precios.
Tipo(5)
Proveedor(16)
Capacidades(12)

Coming soon: the fast Kling 4.0 model. 3-20s at 720p, text-to-video, image-to-video, Omni Reference.
Ver detallesKling 4.0 Flash
Kling
Coming soon: the fast Kling 4.0 model. 3-20s at 720p, text-to-video, image-to-video, Omni Reference.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

Coming soon: 5-20s video with native audio, up to 10 keyframes, video continuation, draft mode.
Ver detallesFLUX 3 Video
Black Forest Labs
Coming soon: 5-20s video with native audio, up to 10 keyframes, video continuation, draft mode.
- Texto a vídeo
- Imagen a vídeo
- Vídeo a vídeo

3-30s video with stereo audio, up to 10 reference images, keyframes, 21:9, multi-shot. 10% launch sale.
Probar este modeloKling 4.0
Kling
3-30s video with stereo audio, up to 10 reference images, keyframes, 21:9, multi-shot. 10% launch sale.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo

#1 on the Vals Index (68.9%), 77.9% DeepSWE v1.1, 91.7% LVBench, 1M context.
Probar este modeloGemini 4 Argon
#1 on the Vals Index (68.9%), 77.9% DeepSWE v1.1, 91.7% LVBench, 1M context.
- Texto a texto

Up to 15 reference images and 3 voice references, 540p to 4K, 1-16s, native audio.
Probar este modeloVidu Q4
Vidu
Up to 15 reference images and 3 voice references, 540p to 4K, 1-16s, native audio.
- Imagen a vídeo
- Referencia a vídeo

#2 on Artificial Analysis TTS arena, audio tags, multi-speaker dialogue, per-request voice cloning.
Probar este modeloEleven v4
ElevenLabs
#2 on Artificial Analysis TTS arena, audio tags, multi-speaker dialogue, per-request voice cloning.
- Texto a voz

#1 on Artificial Analysis TTS arena, ~100 ms median inference, audio tags, dialogue, voice cloning.
Probar este modeloEleven v4 Turbo
ElevenLabs
#1 on Artificial Analysis TTS arena, ~100 ms median inference, audio tags, dialogue, voice cloning.
- Texto a voz

Eleven v4 and v4 Turbo TTS, multi-voice dialogue, sound effects, vocal isolation, speech-to-text.
Probar este modeloElevenLabs
ElevenLabs
Eleven v4 and v4 Turbo TTS, multi-voice dialogue, sound effects, vocal isolation, speech-to-text.
- Texto a voz
- Efectos de sonido
- Voz a texto

Up to 9 image/video/audio references, T2V or first/last frame, 4–15s, up to 4K on Pro.
Probar este modeloSeeDance 2.0
ByteDance
Up to 9 image/video/audio references, T2V or first/last frame, 4–15s, up to 4K on Pro.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo
- Edición de video

Up to 9 references, T2V or first/last frame, 4–15s, 480p or 720p, cost-optimized.
Probar este modeloSeeDance 2.0 Mini
ByteDance
Up to 9 references, T2V or first/last frame, 4–15s, 480p or 720p, cost-optimized.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo
- Edición de video

Up to 9 references, T2V or first/last frame, 4–15s at 480p or 720p, faster turnaround.
Probar este modeloSeeDance 2.0 Fast
ByteDance
Up to 9 references, T2V or first/last frame, 4–15s at 480p or 720p, faster turnaround.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo
- Edición de video

Generate music, extend songs, add vocals, isolate stems, and write lyrics.
Probar este modeloSuno
Suno
Generate music, extend songs, add vocals, isolate stems, and write lyrics.
- Música
- Efectos de sonido

1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking.
Probar este modeloClaude Haiku 5.5
Anthropic
1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking.
- Texto a texto

Nano Banana 2.1: 1K, 2K, or 4K output, 5 aspect ratios plus auto, up to 10 references.
Probar este modeloNano Banana 2.1
Nano Banana 2.1: 1K, 2K, or 4K output, 5 aspect ratios plus auto, up to 10 references.
- Texto a imagen
- Imagen a imagen

Elo 1267 on Artificial Analysis TTS, vocal bursts, two-speaker dialogue, 130+ languages.
Probar este modeloGemini 3.8 Flash TTS
Elo 1267 on Artificial Analysis TTS, vocal bursts, two-speaker dialogue, 130+ languages.
- Texto a voz

The high-volume Gemini 3.8 voice, Elo 1241 on Artificial Analysis TTS, 100+ languages.
Probar este modeloGemini 3.8 Flash Lite TTS
The high-volume Gemini 3.8 voice, Elo 1241 on Artificial Analysis TTS, 100+ languages.
- Texto a voz

Near-Astra coding and computer use at a fifth of Astra's price, 75.2% DeepSWE, 1M context, cached input at half GPT 6 Sol's rate.
Probar este modeloGPT 6.1 Sol
OpenAI
Near-Astra coding and computer use at a fifth of Astra's price, 75.2% DeepSWE, 1M context, cached input at half GPT 6 Sol's rate.
- Texto a texto

1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5.
Probar este modeloClaude Sonnet 5.5
Anthropic
1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5.
- Texto a texto

1M context, image input, 56.4% Agents' Last Exam at 60% less per task than Opus 5, half the price of GPT 5.6 Sol.
Probar este modeloGPT 6 Sol
OpenAI
1M context, image input, 56.4% Agents' Last Exam at 60% less per task than Opus 5, half the price of GPT 5.6 Sol.
- Texto a texto

OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5.
Probar este modeloGPT 6 Luna
OpenAI
OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5.
- Texto a texto

1M context, 384K max output, 552B MoE with 16B active, 74.2% DeepSWE v1.1.
Probar este modeloDeepSeek V4.1 Flash
DeepSeek
1M context, 384K max output, 552B MoE with 16B active, 74.2% DeepSWE v1.1.
- Texto a texto

1.6T MoE with 49B active, 1M context, 384K max output, thinking on by default.
Probar este modeloDeepSeek V4 Pro
DeepSeek
1.6T MoE with 49B active, 1M context, 384K max output, thinking on by default.
- Texto a texto

Versioned V4 Flash ID, now answered by V4.1 Flash. 1M context, 384K max output.
Probar este modeloDeepSeek V4 Flash
DeepSeek
Versioned V4 Flash ID, now answered by V4.1 Flash. 1M context, 384K max output.
- Texto a texto

1M context, 128k output, 66.4% Terminal-Bench 4.0.
Probar este modeloClaude Opus 5.5
Anthropic
1M context, 128k output, 66.4% Terminal-Bench 4.0.
- Texto a texto

500k context, image input, four reasoning efforts, 46.3% CursorBench 4.0, #5 Harvey Legal Agent.
Probar este modeloGrok 4.7
xAI
500k context, image input, four reasoning efforts, 46.3% CursorBench 4.0, #5 Harvey Legal Agent.
- Texto a texto

Flare for speed, Sunburst for edit precision: 1K/2K/4K, 15 aspect ratios, 16 reference images, transparent output.
Probar este modeloGPT Image 2.5
OpenAI
Flare for speed, Sunburst for edit precision: 1K/2K/4K, 15 aspect ratios, 16 reference images, transparent output.
- Texto a imagen
- Imagen a imagen

1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam.
Probar este modeloGPT 6 Astra
OpenAI
1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam.
- Texto a texto

1M context, 5 reasoning efforts incl. minimal, 83.6% MCP Atlas, 57.9% Finance Agent v2, 189 tok/s.
Probar este modeloGemini 3.5 Flash
1M context, 5 reasoning efforts incl. minimal, 83.6% MCP Atlas, 57.9% Finance Agent v2, 189 tok/s.
- Texto a texto

1M context, four reasoning efforts, 73.7% DeepSWE v1.1, 89.4% Terminal-Bench 2.1, 305 tok/s.
Probar este modeloGemini 3.8 Flash
1M context, four reasoning efforts, 73.7% DeepSWE v1.1, 89.4% Terminal-Bench 2.1, 305 tok/s.
- Texto a texto

1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2.
Probar este modeloClaude Fable 5.1
Anthropic
1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2.
- Texto a texto

500k context, image input, three reasoning efforts, 79.3% Terminal-Bench 2.1, trained with Cursor.
Probar este modeloGrok 4.5
xAI
500k context, image input, three reasoning efforts, 79.3% Terminal-Bench 2.1, trained with Cursor.
- Texto a texto

1M context, image input, four reasoning efforts incl. none, 115.8 tok/s, 98% Tau2-Bench Telecom.
Probar este modeloGrok 4.3
xAI
1M context, image input, four reasoning efforts incl. none, 115.8 tok/s, 98% Tau2-Bench Telecom.
- Texto a texto

256k context, image input, agentic coding with function calling and MCP, 0.53s first token.
Probar este modeloGrok Build 0.1
xAI
256k context, image input, agentic coding with function calling and MCP, 0.53s first token.
- Texto a texto

1M context, image input, thinking on, agentic tool calling, 98.9 tok/s, 72.2% SWE-bench Verified.
Probar este modeloGrok 4.20 Reasoning
xAI
1M context, image input, thinking on, agentic tool calling, 98.9 tok/s, 72.2% SWE-bench Verified.
- Texto a texto

1M context, image input, no thinking phase, 0.64s first token, 95.8 tok/s, agentic tool calling.
Probar este modeloGrok 4.20 Non-Reasoning
xAI
1M context, image input, no thinking phase, 0.64s first token, 95.8 tok/s, agentic tool calling.
- Texto a texto

Leader agent plus 4 or 16 sub-agents in parallel, 1M context, image input, Responses API only.
Probar este modeloGrok 4.20 Multi-Agent
xAI
Leader agent plus 4 or 16 sub-agents in parallel, 1M context, image input, Responses API only.
- Texto a texto

Text, image, and character references with voice presets; 4-10s videos plus conversational editing.
Probar este modeloGemini Omni Flash 1.1
Text, image, and character references with voice presets; 4-10s videos plus conversational editing.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Edición de video

Fast Wan 3.0: same 2–30s videos with audio and T2V/I2V/R2V modes, much shorter generation times.
Probar este modeloWan 3.0 Prime
Alibaba
Fast Wan 3.0: same 2–30s videos with audio and T2V/I2V/R2V modes, much shorter generation times.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

Inline audio tags, two-speaker dialogue, 30 voices, 70+ languages.
Probar este modeloGemini 3.1 Flash TTS
Inline audio tags, two-speaker dialogue, 30 voices, 70+ languages.
- Texto a voz

High-quality narration with 30 voices, dialogue mode, and 70+ languages.
Probar este modeloGemini 2.5 Pro TTS
High-quality narration with 30 voices, dialogue mode, and 70+ languages.
- Texto a voz

Fastest, lowest cost per second, with 30 voices and dialogue mode.
Probar este modeloGemini 2.5 Flash TTS
Fastest, lowest cost per second, with 30 voices and dialogue mode.
- Texto a voz

2–30s videos with audio, T2V/I2V/R2V, document and webpage inputs, up to 20 references, 480P–1080P.
Probar este modeloWan 3.0
Alibaba
2–30s videos with audio, T2V/I2V/R2V, document and webpage inputs, up to 20 references, 480P–1080P.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

500k context, image input, four reasoning efforts, 95.6% SWE-bench Verified, #1 CursorBench 3.2.
Probar este modeloGrok 4.6
xAI
500k context, image input, four reasoning efforts, 95.6% SWE-bench Verified, #1 CursorBench 3.2.
- Texto a texto

1M context, 64k output, text/image/audio/video input, ~340 tok/s, 97% MRCR long-context recall.
Probar este modeloGemini 3.7 Flash
1M context, 64k output, text/image/audio/video input, ~340 tok/s, 97% MRCR long-context recall.
- Texto a texto

Quality-focused xAI text-to-image and reference editing with up to 5 input images.
Probar este modeloGrok Imagine 2.0 Image
xAI
Quality-focused xAI text-to-image and reference editing with up to 5 input images.
- Texto a imagen
- Imagen a imagen

1M context, 65k output, multimodal input, 83% OSWorld-Verified, 234 tok/s output speed.
Probar este modeloGemini 3.6 Flash
1M context, 65k output, multimodal input, 83% OSWorld-Verified, 234 tok/s output speed.
- Texto a texto

Animate a start image, 1–15s, 480p to 1080p, the only Grok route that reaches 1080p.
Probar este modeloGrok Imagine 1.5 Video
xAI
Animate a start image, 1–15s, 480p to 1080p, the only Grok route that reaches 1080p.
- Imagen a vídeo

4-30s, 480p to 1080p, native audio, first/last frames, and up to 50 multimodal references.
Probar este modeloSeeDance 2.5
ByteDance
4-30s, 480p to 1080p, native audio, first/last frames, and up to 50 multimodal references.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo
- Edición de video

2K at 24 fps with native audio, 4-15s, six aspect ratios, start/end frames, and reference-to-video.
Probar este modeloMiniMax Hailuo H3
MiniMax
2K at 24 fps with native audio, 4-15s, six aspect ratios, start/end frames, and reference-to-video.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3.
Probar este modeloClaude Opus 5
Anthropic
1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3.
- Texto a texto

2.8T parameters, open weights, 1M context, 131k default output, always-on thinking.
Probar este modeloKimi K3
Moonshot AI
2.8T parameters, open weights, 1M context, 131k default output, always-on thinking.
- Texto a texto

1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode.
Probar este modeloGPT 5.6 Sol
OpenAI
1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode.
- Texto a texto

1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam.
Probar este modeloGPT 5.6 Terra
OpenAI
1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam.
- Texto a texto

Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding.
Probar este modeloGPT 5.6 Luna
OpenAI
Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding.
- Texto a texto

Up to 10 reference images, 8 aspect ratios, 1K/1.5K/2K output, one image per call.
Probar este modeloSeeDream 5.0 Pro
ByteDance
Up to 10 reference images, 8 aspect ratios, 1K/1.5K/2K output, one image per call.
- Texto a imagen
- Imagen a imagen

1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank.
Probar este modeloClaude Fable 5
Anthropic
1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank.
- Texto a texto

200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking.
Probar este modeloClaude Sonnet 4.5
Anthropic
200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking.
- Texto a texto

200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high.
Probar este modeloClaude Opus 4.5
Anthropic
200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high.
- Texto a texto

200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking.
Probar este modeloClaude Haiku 4.5
Anthropic
200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking.
- Texto a texto

Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified.
Probar este modeloClaude Sonnet 5
Anthropic
Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified.
- Texto a texto

Sub-2s generation, 14 aspect ratios, 1K output, up to 14 reference images.
Probar este modeloNano Banana 2 Lite
Sub-2s generation, 14 aspect ratios, 1K output, up to 14 reference images.
- Texto a imagen
- Imagen a imagen

Up to 9 ref images, 720p or 1080p, 3–15s, native audio and lip-sync in one pass.
Probar este modeloHappyHorse 1.1
Alibaba
Up to 9 ref images, 720p or 1080p, 3–15s, native audio and lip-sync in one pass.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

T2V or I2V, 3–15s at 720p Standard or 1080p Pro, no multi-shot or native audio.
Probar este modeloKling 3.0 Turbo
Kling
T2V or I2V, 3–15s at 720p Standard or 1080p Pro, no multi-shot or native audio.
- Texto a vídeo
- Imagen a vídeo

1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking.
Probar este modeloClaude Opus 4.8
Anthropic
1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking.
- Texto a texto

Agentic coding, 79.8% SWE-Bench Multilingual, 69.3% Terminal-Bench 2.0, tuned for long agent runs.
Probar este modeloComposer 2.5
Cursor
Agentic coding, 79.8% SWE-Bench Multilingual, 69.3% Terminal-Bench 2.0, tuned for long agent runs.
- Texto a texto

Low-latency default variant of Composer 2.5, same intelligence, 79.8% SWE-bench Multilingual.
Probar este modeloComposer 2.5 Fast
Cursor
Low-latency default variant of Composer 2.5, same intelligence, 79.8% SWE-bench Multilingual.
- Texto a texto

T2V, I2V, or R2V up to 9 reference images, 720P or 1080P, 3–15s videos with joint audio-video.
Probar este modeloHappyHorse 1.0
Alibaba
T2V, I2V, or R2V up to 9 reference images, 720P or 1080P, 3–15s videos with joint audio-video.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2.
Probar este modeloGPT 5.5
OpenAI
1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2.
- Texto a texto

T2I or reference editing, 5 aspect ratios, 1K, 2K, or 4K resolution control.
Probar este modeloGPT Image 2
OpenAI
T2I or reference editing, 5 aspect ratios, 1K, 2K, or 4K resolution control.
- Texto a imagen
- Imagen a imagen

1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input.
Probar este modeloClaude Opus 4.7
Anthropic
1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input.
- Texto a texto

T2I or editing up to 2K, thinking mode for better quality, up to 9 reference images.
Probar este modeloWan 2.7 Image
Alibaba
T2I or editing up to 2K, thinking mode for better quality, up to 9 reference images.
- Texto a imagen
- Imagen a imagen

T2I or editing up to 4K, thinking mode for better quality, up to 9 reference images.
Probar este modeloWan 2.7 Image Pro
Alibaba
T2I or editing up to 4K, thinking mode for better quality, up to 9 reference images.
- Texto a imagen
- Imagen a imagen

T2V, I2V, or R2V with first/last frame, video continuation, lip-sync, 2–15s at 720P or 1080P.
Probar este modeloWan 2.7
Alibaba
T2V, I2V, or R2V with first/last frame, video continuation, lip-sync, 2–15s at 720P or 1080P.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo

Edit 2–10s videos with up to 4 reference images at 720P or 1080P, plus audio passthrough.
Probar este modeloWan 2.7 Video Edit
Alibaba
Edit 2–10s videos with up to 4 reference images at 720P or 1080P, plus audio passthrough.
- Edición de video

400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini.
Probar este modeloGPT 5.4 Mini
OpenAI
400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini.
- Texto a texto

400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh.
Probar este modeloGPT 5.4 Nano
OpenAI
400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh.
- Texto a texto

Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents.
Probar este modeloGPT 5.4
OpenAI
Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents.
- Texto a texto

1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking.
Probar este modeloClaude Sonnet 4.6
Anthropic
1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking.
- Texto a texto

Edit a 3–60s video by prompt, swap objects from up to 5 reference images, keep the original audio.
Probar este modeloHappyHorse 1.0 Video Edit
Alibaba
Edit a 3–60s video by prompt, swap objects from up to 5 reference images, keep the original audio.
- Edición de video

1M context, 128k output, effort controls, top Arena Document and Search rank.
Probar este modeloClaude Opus 4.6
Anthropic
1M context, 128k output, effort controls, top Arena Document and Search rank.
- Texto a texto

Multi-shot 2–6 scenes per call, 3–15s single-shot, 4K mode, with Audio 2.0 lip-sync.
Probar este modeloKling 3.0
Kling
Multi-shot 2–6 scenes per call, 3–15s single-shot, 4K mode, with Audio 2.0 lip-sync.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

Motion transfer onto a character with high facial consistency, 720p Std or 1080p Pro.
Probar este modeloKling 3.0 Motion Control
Kling
Motion transfer onto a character with high facial consistency, 720p Std or 1080p Pro.
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo

T2I or editing with up to 10 reference images, 9 aspect ratios incl. auto, and 1K to 4K.
Probar este modeloKling 3.0 Omni Image
Kling
T2I or editing with up to 10 reference images, 9 aspect ratios incl. auto, and 1K to 4K.
- Texto a imagen
- Imagen a imagen

Up to 7 references plus elements, video reference/transform, multi-shot 2–6, 4K mode.
Probar este modeloKling 3.0 Omni
Kling
Up to 7 references plus elements, video reference/transform, multi-shot 2–6, 4K mode.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo

Edit videos with reference (style guide) or transform mode, plus image and video elements.
Probar este modeloKling 3.0 Omni Edit
Kling
Edit videos with reference (style guide) or transform mode, plus image and video elements.
- Edición de video

Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
Probar este modeloSeeDream 5.0 Lite
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- Texto a imagen
- Imagen a imagen

T2I with Chinese and English text rendering, 7 aspect ratios. No editing.
Probar este modeloZ-Image Turbo
Alibaba
T2I with Chinese and English text rendering, 7 aspect ratios. No editing.
- Texto a imagen

T2V, I2V, or R2V up to 5 references, 720p or 1080p, 2–15s, with auto audio and multi-shot.
Probar este modeloWan 2.6
Alibaba
T2V, I2V, or R2V up to 5 references, 720p or 1080p, 2–15s, with auto audio and multi-shot.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

Faster Wan 2.6 with T2V/I2V/R2V, multi-shot, and auto-audio up to 1080p.
Probar este modeloWan 2.6 Flash
Alibaba
Faster Wan 2.6 with T2V/I2V/R2V, multi-shot, and auto-audio up to 1080p.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

T2I, editing, or style transfer with 1–4 reference images and 7 aspect ratios.
Probar este modeloWan 2.6 Image
Alibaba
T2I, editing, or style transfer with 1–4 reference images and 7 aspect ratios.
- Texto a imagen
- Imagen a imagen

Transfer motion from a reference video onto a character image, 720p Std or 1080p Pro.
Probar este modeloKling 2.6 Control de Movimiento
Kling
Transfer motion from a reference video onto a character image, 720p Std or 1080p Pro.
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo

T2V or I2V at 720p Standard or 1080p Pro, 5 or 10s, with optional end frame and audio.
Probar este modeloKling 2.6
Kling
T2V or I2V at 720p Standard or 1080p Pro, 5 or 10s, with optional end frame and audio.
- Texto a vídeo
- Imagen a vídeo

Balanced production runs, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
Probar este modeloFlux.2 Pro
Black Forest Labs
Balanced production runs, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
- Texto a imagen
- Imagen a imagen

9B Flux.2 Klein, 7 aspect ratios up to 4MP, reference image support.
Probar este modeloFlux.2 Klein 9B
Black Forest Labs
9B Flux.2 Klein, 7 aspect ratios up to 4MP, reference image support.
- Texto a imagen
- Imagen a imagen

4B Flux.2 Klein, smallest in the line, 7 aspect ratios up to 4MP, reference image support.
Probar este modeloFlux.2 Klein 4B
Black Forest Labs
4B Flux.2 Klein, smallest in the line, 7 aspect ratios up to 4MP, reference image support.
- Texto a imagen
- Imagen a imagen

T2I plus multi-image fusion editing, 5 aspect ratios, smart prompt rewriting on by default.
Probar este modeloQwen Image 2.0
Alibaba
T2I plus multi-image fusion editing, 5 aspect ratios, smart prompt rewriting on by default.
- Texto a imagen
- Imagen a imagen

Text rendering, multi-image fusion editing, 5 aspect ratios, highest output in the line.
Probar este modeloQwen Image 2.0 Pro
Alibaba
Text rendering, multi-image fusion editing, 5 aspect ratios, highest output in the line.
- Texto a imagen
- Imagen a imagen

Reasoning video gen with up to 7 references, image-only elements, single-shot 3–10s, 720p/1080p.
Probar este modeloKling O1
Kling
Reasoning video gen with up to 7 references, image-only elements, single-shot 3–10s, 720p/1080p.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo

Reasoning image gen with up to 10 reference images, 9 aspect ratios, and 1K or 2K output.
Probar este modeloKling O1 Image
Kling
Reasoning image gen with up to 10 reference images, 9 aspect ratios, and 1K or 2K output.
- Texto a imagen
- Imagen a imagen

Reasoning video editing with reference or transform mode, up to 4 reference images.
Probar este modeloKling O1 Edit
Kling
Reasoning video editing with reference or transform mode, up to 4 reference images.
- Edición de video

Gemini 3 image gen with 1K, 2K, or 4K, 10 aspect ratios, and reference image support.
Probar este modeloNano Banana Pro
Gemini 3 image gen with 1K, 2K, or 4K, 10 aspect ratios, and reference image support.
- Texto a imagen
- Imagen a imagen

T2V or I2V with optional end frame, 5 or 10s at 720p Standard or 1080p Pro.
Probar este modeloKling 2.5 Turbo
Kling
T2V or I2V with optional end frame, 5 or 10s at 720p Standard or 1080p Pro.
- Texto a vídeo
- Imagen a vídeo

Animates a start frame from your prompt, 768p or 1080p, 6 or 10 seconds.
Probar este modeloMiniMax Hailuo 2.3
MiniMax
Animates a start frame from your prompt, 768p or 1080p, 6 or 10 seconds.
- Imagen a vídeo

Image-led speed variant, start image required, 768p or 1080p, 6 or 10 seconds.
Probar este modeloMiniMax Hailuo 2.3 Fast
MiniMax
Image-led speed variant, start image required, 768p or 1080p, 6 or 10 seconds.
- Imagen a vídeo

Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
Probar este modeloSeeDream 4.5
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- Texto a imagen
- Imagen a imagen

4 model variants, 720p–4K, lip-synced dialogue and SFX in one call.
Probar este modeloVeo 3.1
4 model variants, 720p–4K, lip-synced dialogue and SFX in one call.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo
- Vídeo a vídeo

Gemini image gen with 1K, 2K, or 4K resolution control and 10 aspect ratios.
Probar este modeloNano Banana 2
Gemini image gen with 1K, 2K, or 4K resolution control and 10 aspect ratios.
- Texto a imagen
- Imagen a imagen

T2I or editing with 1–3 reference images, 7 aspect ratios, prompt extend on by default.
Probar este modeloWan 2.5 Image
Alibaba
T2I or editing with 1–3 reference images, 7 aspect ratios, prompt extend on by default.
- Texto a imagen
- Imagen a imagen

T2V or I2V at 480p, 720p, or 1080p, 5 or 10s, with auto audio or custom audio sync.
Probar este modeloWan 2.5
Alibaba
T2V or I2V at 480p, 720p, or 1080p, 5 or 10s, with auto audio or custom audio sync.
- Texto a vídeo
- Imagen a vídeo

T2I plus reference editing, 5 aspect ratios, smart prompt rewriting, negative prompts.
Probar este modeloQwen Image
Alibaba
T2I plus reference editing, 5 aspect ratios, smart prompt rewriting, negative prompts.
- Texto a imagen
- Imagen a imagen

Photoreal T2I plus reference editing, 5 aspect ratios, fewest synthetic artifacts in line.
Probar este modeloQwen Image Max
Alibaba
Photoreal T2I plus reference editing, 5 aspect ratios, fewest synthetic artifacts in line.
- Texto a imagen
- Imagen a imagen

Stylistic T2I plus reference editing, 5 aspect ratios, fast sampling for design exploration.
Probar este modeloQwen Image Plus
Alibaba
Stylistic T2I plus reference editing, 5 aspect ratios, fast sampling for design exploration.
- Texto a imagen
- Imagen a imagen

Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
Probar este modeloSeeDream 4.0
ByteDance
Up to 6 reference images, 8 aspect ratios, 2K or 4K, returns 4 images per call.
- Texto a imagen
- Imagen a imagen

T2V or first/last frame at 720p or 1080p, with 5, 10, or 12s videos.
Probar este modeloSeeDance 1.5 Pro
ByteDance
T2V or first/last frame at 720p or 1080p, with 5, 10, or 12s videos.
- Texto a vídeo
- Imagen a vídeo

Start frame, end frame, or both, 512p, 768p or 1080p, 6 or 10 seconds.
Probar este modeloMiniMax Hailuo 2.0
MiniMax
Start frame, end frame, or both, 512p, 768p or 1080p, 6 or 10 seconds.
- Imagen a vídeo

Text-to-image only, 5 aspect ratios, negative prompts and seeds for reproducible output.
Probar este modeloWan 2.2 Image
Alibaba
Text-to-image only, 5 aspect ratios, negative prompts and seeds for reproducible output.
- Texto a imagen

Cheapest T2I in the Wan line, 5 aspect ratios, negative prompts and seeds. No editing.
Probar este modeloWan 2.2 Image Flash
Alibaba
Cheapest T2I in the Wan line, 5 aspect ratios, negative prompts and seeds. No editing.
- Texto a imagen

Silent T2V or I2V, fixed 5s videos at 480p or 1080p, with negative prompts and seeds.
Probar este modeloWan 2.2
Alibaba
Silent T2V or I2V, fixed 5s videos at 480p or 1080p, with negative prompts and seeds.
- Texto a vídeo
- Imagen a vídeo

Fastest Wan 2.2 silent T2V/I2V, fixed 5s videos, with I2V at 720p in addition to 480p/1080p.
Probar este modeloWan 2.2 Fast
Alibaba
Fastest Wan 2.2 silent T2V/I2V, fixed 5s videos, with I2V at 720p in addition to 480p/1080p.
- Texto a vídeo
- Imagen a vídeo

Deprecated original Nano Banana (Gemini 2.5 Flash Image). Use Nano Banana 2.1 for new work.
Probar este modeloNano Banana
Deprecated original Nano Banana (Gemini 2.5 Flash Image). Use Nano Banana 2.1 for new work.
- Texto a imagen
- Imagen a imagen

Upscale to 480p–8K with 21 Topaz model presets, optional frame interpolation, source FPS preserved by default.
Probar este modeloTopaz Video Upscale
Topaz Labs
Upscale to 480p–8K with 21 Topaz model presets, optional frame interpolation, source FPS preserved by default.
- Vídeo a vídeo

AI image upscale 1x–16x with denoise, sharpen, and face enhancement controls.
Probar este modeloTopaz Image Upscale
Topaz Labs
AI image upscale 1x–16x with denoise, sharpen, and face enhancement controls.
- Imagen a imagen

T2V or I2V at Pro 1080p only, 5 or 10s, with optional sound effects and music.
Probar este modeloKling 2.1 Master
Kling
T2V or I2V at Pro 1080p only, 5 or 10s, with optional sound effects and music.
- Texto a vídeo
- Imagen a vídeo

Extend a finished Grok Imagine video by 6 or 10 seconds, preset or custom mode.
Probar este modeloGrok Imagine Video Extend
xAI
Extend a finished Grok Imagine video by 6 or 10 seconds, preset or custom mode.
- Vídeo a vídeo

Upscale a finished Grok Imagine video to HD from its task ID.
Probar este modeloGrok Imagine Upscale
xAI
Upscale a finished Grok Imagine video to HD from its task ID.
- Vídeo a vídeo

I2V with optional end frame, 5 or 10s, Standard 720p or Pro 1080p, optional sound effects.
Probar este modeloKling 2.1
Kling
I2V with optional end frame, 5 or 10s, Standard 720p or Pro 1080p, optional sound effects.
- Imagen a vídeo

T2V or I2V at 480p/720p, 5 or 10 second clips.
Probar este modeloSeeDance 1.0
ByteDance
T2V or I2V at 480p/720p, 5 or 10 second clips.
- Texto a vídeo
- Imagen a vídeo

First- and last-frame video generation at 480p, 720p, or 1080p for 4–12 seconds.
Probar este modeloSeeDance 1.0 Pro
ByteDance
First- and last-frame video generation at 480p, 720p, or 1080p for 4–12 seconds.
- Imagen a vídeo

Fast text-to-video and first-frame image-to-video at up to 1080p for 4–12 seconds.
Probar este modeloSeeDance 1.0 Pro Fast
ByteDance
Fast text-to-video and first-frame image-to-video at up to 1080p for 4–12 seconds.
- Texto a vídeo
- Imagen a vídeo

Steps, guidance, seed, and prompt upsampling controls, 7 aspect ratios up to 4 MP.
Probar este modeloFlux.2 Flex
Black Forest Labs
Steps, guidance, seed, and prompt upsampling controls, 7 aspect ratios up to 4 MP.
- Texto a imagen
- Imagen a imagen

Maximum quality Flux.2 output, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
Probar este modeloFlux.2 Max
Black Forest Labs
Maximum quality Flux.2 output, 7 aspect ratios, 0.6-4 MP, up to 10 reference images.
- Texto a imagen
- Imagen a imagen

T2V, I2V, or reference images with style presets, faster results at 480p, 720p, or 1080p.
Probar este modeloGrok Imagine 1.5 Video Fast
xAI
T2V, I2V, or reference images with style presets, faster results at 480p, 720p, or 1080p.
- Texto a vídeo
- Imagen a vídeo
- Referencia a vídeo

Fast xAI text-to-image and reference editing with up to 5 images.
Probar este modeloGrok Imagine 1.0 Image
xAI
Fast xAI text-to-image and reference editing with up to 5 images.
- Texto a imagen
- Imagen a imagen
Browse model families
APIs por tarea
All models A–Z
Every model and variant on the platform, including the specialised routes that sit inside a family page.